Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

预训练代码和是否使用预训练权重训练效果差别问题 #31

Open
weizhiyangq opened this issue Apr 1, 2024 · 0 comments

Comments

@weizhiyangq
Copy link

weizhiyangq commented Apr 1, 2024

导,有两个问题想请问一下您:
1.没有使用预训练,跑了100epoch,mIoU: 从3.6左右变到4.28,但 Accuracy:从开始到结束一直是73.43左右?,测试效果惨不忍睹,基本分割不出什么,请问为什么会这样呢,效果不好可以理解,但好像分割图好像基本无效。以前使用FCN这些cnn网络效果都还可以。是因为segformer参数太多吗?还是transformer类的模型都这样?
2.请问可以分享一下预训练的代码吗?
谢谢!

@weizhiyangq weizhiyangq changed the title 训练accuracy不变问题 预训练代码和是否使用预训练权重训练效果差别问题 Apr 2, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant